전체 검색

AI 모델 84759

• Tesslate_Tessa-T1-32B-GGUF↗

  bartowski

• Kimi-2.5-text-nvfp4-v6-mlp-only↗

  baseten-admin

• sooktam2↗

  bharatgenai

• diarizen-wavlm-large-s80-md-v2↗

  BUT-FIT

• nethack-vae↗

  CatkinChen

• qwen3-coder-30b-a3b-compacted-19b-256k↗

  continuum-ai

• surya-ocr-2-gguf↗

  datalab-to

  - Accuracy - scores 83.3% on olmOCR-bench (top under 3B params) - Speed - throughput of 5 pages/s on an RTX 5090 - Multilingual - scores 87.2% on an internal benchmark set of 91 languages (more here) - Layout analysis (table, image, header, etc.) with reading order - Table recognition (rows + columns) It works on a range of documents (see usage and benchmarks). Our managed platform runs both Surya, and variants of our highest accuracy model, Chandra.

• Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking↗

  DavidAU

• Birds-Classifier-EfficientNetB2↗

  dennisjooo

• MagenticBrain-GGUF↗

  devehz